#!/usr/bin/env bash
# End-to-end test: upload Parquet → register dataset → SQL query
set -e

BASE="http://localhost:3100"

echo "=== Generate test Parquet file ==="
python3 -c "
import struct, io

# Minimal Parquet via pyarrow if available, else skip
try:
    import pyarrow as pa
    import pyarrow.parquet as pq
    table = pa.table({
        'id': [1, 2, 3, 4, 5],
        'name': ['alice', 'bob', 'carol', 'dave', 'eve'],
        'score': [9.5, 8.2, 7.8, 6.1, 9.9],
    })
    pq.write_table(table, '/tmp/test_data.parquet')
    print('generated with pyarrow')
except ImportError:
    print('pyarrow not available, generating via rust helper')
    exit(1)
"

echo "=== Upload Parquet to storage ==="
curl -s -X PUT "$BASE/storage/objects/datasets/scores.parquet" \
  --data-binary @/tmp/test_data.parquet
echo ""

echo "=== Register dataset in catalog ==="
SIZE=$(stat -c%s /tmp/test_data.parquet)
curl -s -X POST "$BASE/catalog/datasets" \
  -H "Content-Type: application/json" \
  -d "{\"name\":\"scores\",\"schema_fingerprint\":\"test\",\"objects\":[{\"bucket\":\"data\",\"key\":\"datasets/scores.parquet\",\"size_bytes\":$SIZE}]}" | python3 -m json.tool
echo ""

echo "=== SQL: SELECT * FROM scores ==="
curl -s -X POST "$BASE/query/sql" \
  -H "Content-Type: application/json" \
  -d '{"sql":"SELECT * FROM scores"}' | python3 -m json.tool
echo ""

echo "=== SQL: SELECT name, score FROM scores WHERE score > 8.0 ORDER BY score DESC ==="
curl -s -X POST "$BASE/query/sql" \
  -H "Content-Type: application/json" \
  -d '{"sql":"SELECT name, score FROM scores WHERE score > 8.0 ORDER BY score DESC"}' | python3 -m json.tool
echo ""

echo "=== SQL: SELECT COUNT(*), AVG(score) FROM scores ==="
curl -s -X POST "$BASE/query/sql" \
  -H "Content-Type: application/json" \
  -d '{"sql":"SELECT COUNT(*) as cnt, AVG(score) as avg_score FROM scores"}' | python3 -m json.tool
echo ""

echo "=== DONE ==="